Edit model card

Model Details

Model has been quantized on 6xRTX4090, here are quantization parameters:

"zero_point": True, "q_group_size": 128, "w_bit": 4, "version": "GEMV"

Safetensors

Model size

5.4B params

Tensor type

I32

FP16

Inference Examples

Unable to determine this model's library. Check the docs .

Model tree for andriadze/anthracite-magnum-v3-34b-awq-gemv

Base model

Quantized

(7)

this model